Using Linguistic Inquiry and Word Count Software to Analyze Group Interaction Language Data

Objective: Automated text analysis tools can uncover emergent group processes from communication data. The article presents an illustration aimed at novice users of how the Linguistic Inquiry and Word Count (LIWC) software tool reveals group processes from interaction data collected. Using a data set from published research, we apply the group interaction model (GIM) to illustrate how to operationalize a group interaction hypothesis from the variables provided by LIWC. Then, we guide the reader through the steps of preparing transcripts for analysis in LIWC, running the transcripts to get data from LIWC, and then merging spreadsheets into one data set for analysis. In addition, the article provides instructions and resources to manage the complexity of linguistic measures gathered at various time intervals. Method: We provide data preparation tips, instructions for using the fifth-generation version of the LIWC-22 tool to analyze group process data, and resources for combining the LIWC measures to reflect their time interval and to combine them into one file with time-invariant group data. Results: In addition to providing accessible instructions, the article details several applications, such as naturalistic group data gathered across time and pre/post experimental design that increase statistical power. It also provides an annotated bibliography for further reading. Conclusion: The linguistic style of group communication often reveals group dynamics. Using the GIM, this article outlines how to uncover emergent group processes from communication data gathered at time intervals using LIWC-22. Highlights and Implications * The group interaction research landscape has transformed from one of paucity to "big" data abundance, calling for new group language analysis theory and methods. * We illustrate how emergent processes outlined in the group interaction model (GIM) may be converted into linguistic analysis hypotheses that are amendable to automated text analysis. * We discuss what the Linguistic Inquiry and Word Count (LIWC) is and how the variables LIWC-22 provides map onto GIM processes. * A data set from published articles is used to present a step-by-step example with tips to prepare transcripts, instructions on how to analyze transcripts with LIWC-22, and then instructions on how to merge the resulting data sets into a central data set for subsequent statistical analysis. * We provide Supplemental Materials detailing how to (a) use LIWC-22 to segment t